Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 678 insertions, 0 deletions

diff --git a/drivers/media/usb/pwc/pwc-dec23.c b/drivers/media/usb/pwc/pwc-dec23.c
new file mode 100644
index 000000000..a3aa8c717
--- /dev/null
+++ b/drivers/media/usb/pwc/pwc-dec23.c
@@ -0,0 +1,678 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* Linux driver for Philips webcam
+   Decompression for chipset version 2 et 3
+   (C) 2004-2006  Luc Saillard (luc@saillard.org)
+
+   NOTE: this version of pwc is an unofficial (modified) release of pwc & pcwx
+   driver and thus may have bugs that are not present in the original version.
+   Please send bug reports and support requests to <luc@saillard.org>.
+   The decompression routines have been implemented by reverse-engineering the
+   Nemosoft binary pwcx module. Caveat emptor.
+
+
+*/
+
+#include "pwc-timon.h"
+#include "pwc-kiara.h"
+#include "pwc-dec23.h"
+
+#include <linux/string.h>
+#include <linux/slab.h>
+
+/*
+ * USE_LOOKUP_TABLE_TO_CLAMP
+ *   0: use a C version of this tests:  {  a<0?0:(a>255?255:a) }
+ *   1: use a faster lookup table for cpu with a big cache (intel)
+ */
+#define USE_LOOKUP_TABLE_TO_CLAMP	1
+/*
+ * UNROLL_LOOP_FOR_COPYING_BLOCK
+ *   0: use a loop for a smaller code (but little slower)
+ *   1: when unrolling the loop, gcc produces some faster code (perhaps only
+ *   valid for intel processor class). Activating this option, automatically
+ *   activate USE_LOOKUP_TABLE_TO_CLAMP
+ */
+#define UNROLL_LOOP_FOR_COPY		1
+#if UNROLL_LOOP_FOR_COPY
+# undef USE_LOOKUP_TABLE_TO_CLAMP
+# define USE_LOOKUP_TABLE_TO_CLAMP 1
+#endif
+
+static void build_subblock_pattern(struct pwc_dec23_private *pdec)
+{
+	static const unsigned int initial_values[12] = {
+		-0x526500, -0x221200, 0x221200, 0x526500,
+			   -0x3de200, 0x3de200,
+		-0x6db480, -0x2d5d00, 0x2d5d00, 0x6db480,
+			   -0x12c200, 0x12c200
+
+	};
+	static const unsigned int values_derivated[12] = {
+		0xa4ca, 0x4424, -0x4424, -0xa4ca,
+			0x7bc4, -0x7bc4,
+		0xdb69, 0x5aba, -0x5aba, -0xdb69,
+			0x2584, -0x2584
+	};
+	unsigned int temp_values[12];
+	int i, j;
+
+	memcpy(temp_values, initial_values, sizeof(initial_values));
+	for (i = 0; i < 256; i++) {
+		for (j = 0; j < 12; j++) {
+			pdec->table_subblock[i][j] = temp_values[j];
+			temp_values[j] += values_derivated[j];
+		}
+	}
+}
+
+static void build_bit_powermask_table(struct pwc_dec23_private *pdec)
+{
+	unsigned char *p;
+	unsigned int bit, byte, mask, val;
+	unsigned int bitpower = 1;
+
+	for (bit = 0; bit < 8; bit++) {
+		mask = bitpower - 1;
+		p = pdec->table_bitpowermask[bit];
+		for (byte = 0; byte < 256; byte++) {
+			val = (byte & mask);
+			if (byte & bitpower)
+				val = -val;
+			*p++ = val;
+		}
+		bitpower<<=1;
+	}
+}
+
+
+static void build_table_color(const unsigned int romtable[16][8],
+			      unsigned char p0004[16][1024],
+			      unsigned char p8004[16][256])
+{
+	int compression_mode, j, k, bit, pw;
+	unsigned char *p0, *p8;
+	const unsigned int *r;
+
+	/* We have 16 compressions tables */
+	for (compression_mode = 0; compression_mode < 16; compression_mode++) {
+		p0 = p0004[compression_mode];
+		p8 = p8004[compression_mode];
+		r  = romtable[compression_mode];
+
+		for (j = 0; j < 8; j++, r++, p0 += 128) {
+
+			for (k = 0; k < 16; k++) {
+				if (k == 0)
+					bit = 1;
+				else if (k >= 1 && k < 3)
+					bit = (r[0] >> 15) & 7;
+				else if (k >= 3 && k < 6)
+					bit = (r[0] >> 12) & 7;
+				else if (k >= 6 && k < 10)
+					bit = (r[0] >> 9) & 7;
+				else if (k >= 10 && k < 13)
+					bit = (r[0] >> 6) & 7;
+				else if (k >= 13 && k < 15)
+					bit = (r[0] >> 3) & 7;
+				else
+					bit = (r[0]) & 7;
+				if (k == 0)
+					*p8++ = 8;
+				else
+					*p8++ = j - bit;
+				*p8++ = bit;
+
+				pw = 1 << bit;
+				p0[k + 0x00] = (1 * pw) + 0x80;
+				p0[k + 0x10] = (2 * pw) + 0x80;
+				p0[k + 0x20] = (3 * pw) + 0x80;
+				p0[k + 0x30] = (4 * pw) + 0x80;
+				p0[k + 0x40] = (-1 * pw) + 0x80;
+				p0[k + 0x50] = (-2 * pw) + 0x80;
+				p0[k + 0x60] = (-3 * pw) + 0x80;
+				p0[k + 0x70] = (-4 * pw) + 0x80;
+			}	/* end of for (k=0; k<16; k++, p8++) */
+		}	/* end of for (j=0; j<8; j++ , table++) */
+	} /* end of foreach compression_mode */
+}
+
+/*
+ *
+ */
+static void fill_table_dc00_d800(struct pwc_dec23_private *pdec)
+{
+#define SCALEBITS 15
+#define ONE_HALF  (1UL << (SCALEBITS - 1))
+	int i;
+	unsigned int offset1 = ONE_HALF;
+	unsigned int offset2 = 0x0000;
+
+	for (i=0; i<256; i++) {
+		pdec->table_dc00[i] = offset1 & ~(ONE_HALF);
+		pdec->table_d800[i] = offset2;
+
+		offset1 += 0x7bc4;
+		offset2 += 0x7bc4;
+	}
+}
+
+/*
+ * To decode the stream:
+ *   if look_bits(2) == 0:	# op == 2 in the lookup table
+ *      skip_bits(2)
+ *      end of the stream
+ *   elif look_bits(3) == 7:	# op == 1 in the lookup table
+ *      skip_bits(3)
+ *      yyyy = get_bits(4)
+ *      xxxx = get_bits(8)
+ *   else:			# op == 0 in the lookup table
+ *      skip_bits(x)
+ *
+ * For speedup processing, we build a lookup table and we takes the first 6 bits.
+ *
+ * struct {
+ *   unsigned char op;	    // operation to execute
+ *   unsigned char bits;    // bits use to perform operation
+ *   unsigned char offset1; // offset to add to access in the table_0004 % 16
+ *   unsigned char offset2; // offset to add to access in the table_0004
+ * }
+ *
+ * How to build this table ?
+ *   op == 2 when (i%4)==0
+ *   op == 1 when (i%8)==7
+ *   op == 0 otherwise
+ *
+ */
+static const unsigned char hash_table_ops[64*4] = {
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x10,
+	0x00, 0x06, 0x01, 0x30,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x01, 0x20,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x50,
+	0x00, 0x05, 0x02, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x03, 0x00,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x10,
+	0x00, 0x06, 0x02, 0x10,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x01, 0x60,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x50,
+	0x00, 0x05, 0x02, 0x40,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x03, 0x40,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x10,
+	0x00, 0x06, 0x01, 0x70,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x01, 0x20,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x50,
+	0x00, 0x05, 0x02, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x03, 0x00,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x10,
+	0x00, 0x06, 0x02, 0x50,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x01, 0x60,
+	0x01, 0x00, 0x00, 0x00,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x00,
+	0x00, 0x04, 0x01, 0x50,
+	0x00, 0x05, 0x02, 0x40,
+	0x02, 0x00, 0x00, 0x00,
+	0x00, 0x03, 0x01, 0x40,
+	0x00, 0x05, 0x03, 0x40,
+	0x01, 0x00, 0x00, 0x00
+};
+
+/*
+ *
+ */
+static const unsigned int MulIdx[16][16] = {
+	{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,},
+	{0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3,},
+	{0, 0, 0, 0, 1, 1, 1, 1, 2, 2, 2, 2, 3, 3, 3, 3,},
+	{4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5, 4, 4, 4, 4,},
+	{6, 7, 8, 9, 7, 10, 11, 8, 8, 11, 10, 7, 9, 8, 7, 6,},
+	{4, 5, 5, 4, 4, 5, 5, 4, 4, 5, 5, 4, 4, 5, 5, 4,},
+	{1, 3, 0, 2, 1, 3, 0, 2, 1, 3, 0, 2, 1, 3, 0, 2,},
+	{0, 3, 3, 0, 1, 2, 2, 1, 2, 1, 1, 2, 3, 0, 0, 3,},
+	{0, 1, 2, 3, 3, 2, 1, 0, 3, 2, 1, 0, 0, 1, 2, 3,},
+	{1, 1, 1, 1, 3, 3, 3, 3, 0, 0, 0, 0, 2, 2, 2, 2,},
+	{7, 10, 11, 8, 9, 8, 7, 6, 6, 7, 8, 9, 8, 11, 10, 7,},
+	{4, 5, 5, 4, 5, 4, 4, 5, 5, 4, 4, 5, 4, 5, 5, 4,},
+	{7, 9, 6, 8, 10, 8, 7, 11, 11, 7, 8, 10, 8, 6, 9, 7,},
+	{1, 3, 0, 2, 2, 0, 3, 1, 2, 0, 3, 1, 1, 3, 0, 2,},
+	{1, 2, 2, 1, 3, 0, 0, 3, 0, 3, 3, 0, 2, 1, 1, 2,},
+	{10, 8, 7, 11, 8, 6, 9, 7, 7, 9, 6, 8, 11, 7, 8, 10}
+};
+
+#if USE_LOOKUP_TABLE_TO_CLAMP
+#define MAX_OUTER_CROP_VALUE	(512)
+static unsigned char pwc_crop_table[256 + 2*MAX_OUTER_CROP_VALUE];
+#define CLAMP(x) (pwc_crop_table[MAX_OUTER_CROP_VALUE+(x)])
+#else
+#define CLAMP(x) ((x)>255?255:((x)<0?0:x))
+#endif
+
+
+/* If the type or the command change, we rebuild the lookup table */
+void pwc_dec23_init(struct pwc_device *pdev, const unsigned char *cmd)
+{
+	int flags, version, shift, i;
+	struct pwc_dec23_private *pdec = &pdev->dec23;
+
+	mutex_init(&pdec->lock);
+
+	if (pdec->last_cmd_valid && pdec->last_cmd == cmd[2])
+		return;
+
+	if (DEVICE_USE_CODEC3(pdev->type)) {
+		flags = cmd[2] & 0x18;
+		if (flags == 8)
+			pdec->nbits = 7;	/* More bits, mean more bits to encode the stream, but better quality */
+		else if (flags == 0x10)
+			pdec->nbits = 8;
+		else
+			pdec->nbits = 6;
+
+		version = cmd[2] >> 5;
+		build_table_color(KiaraRomTable[version][0], pdec->table_0004_pass1, pdec->table_8004_pass1);
+		build_table_color(KiaraRomTable[version][1], pdec->table_0004_pass2, pdec->table_8004_pass2);
+
+	} else {
+
+		flags = cmd[2] & 6;
+		if (flags == 2)
+			pdec->nbits = 7;
+		else if (flags == 4)
+			pdec->nbits = 8;
+		else
+			pdec->nbits = 6;
+
+		version = cmd[2] >> 3;
+		build_table_color(TimonRomTable[version][0], pdec->table_0004_pass1, pdec->table_8004_pass1);
+		build_table_color(TimonRomTable[version][1], pdec->table_0004_pass2, pdec->table_8004_pass2);
+	}
+
+	/* Information can be coded on a variable number of bits but never less than 8 */
+	shift = 8 - pdec->nbits;
+	pdec->scalebits = SCALEBITS - shift;
+	pdec->nbitsmask = 0xFF >> shift;
+
+	fill_table_dc00_d800(pdec);
+	build_subblock_pattern(pdec);
+	build_bit_powermask_table(pdec);
+
+#if USE_LOOKUP_TABLE_TO_CLAMP
+	/* Build the static table to clamp value [0-255] */
+	for (i=0;i<MAX_OUTER_CROP_VALUE;i++)
+		pwc_crop_table[i] = 0;
+	for (i=0; i<256; i++)
+		pwc_crop_table[MAX_OUTER_CROP_VALUE+i] = i;
+	for (i=0; i<MAX_OUTER_CROP_VALUE; i++)
+		pwc_crop_table[MAX_OUTER_CROP_VALUE+256+i] = 255;
+#endif
+
+	pdec->last_cmd = cmd[2];
+	pdec->last_cmd_valid = 1;
+}
+
+/*
+ * Copy the 4x4 image block to Y plane buffer
+ */
+static void copy_image_block_Y(const int *src, unsigned char *dst, unsigned int bytes_per_line, unsigned int scalebits)
+{
+#if UNROLL_LOOP_FOR_COPY
+	const unsigned char *cm = pwc_crop_table+MAX_OUTER_CROP_VALUE;
+	const int *c = src;
+	unsigned char *d = dst;
+
+	*d++ = cm[c[0] >> scalebits];
+	*d++ = cm[c[1] >> scalebits];
+	*d++ = cm[c[2] >> scalebits];
+	*d++ = cm[c[3] >> scalebits];
+
+	d = dst + bytes_per_line;
+	*d++ = cm[c[4] >> scalebits];
+	*d++ = cm[c[5] >> scalebits];
+	*d++ = cm[c[6] >> scalebits];
+	*d++ = cm[c[7] >> scalebits];
+
+	d = dst + bytes_per_line*2;
+	*d++ = cm[c[8] >> scalebits];
+	*d++ = cm[c[9] >> scalebits];
+	*d++ = cm[c[10] >> scalebits];
+	*d++ = cm[c[11] >> scalebits];
+
+	d = dst + bytes_per_line*3;
+	*d++ = cm[c[12] >> scalebits];
+	*d++ = cm[c[13] >> scalebits];
+	*d++ = cm[c[14] >> scalebits];
+	*d++ = cm[c[15] >> scalebits];
+#else
+	int i;
+	const int *c = src;
+	unsigned char *d = dst;
+	for (i = 0; i < 4; i++, c++)
+		*d++ = CLAMP((*c) >> scalebits);
+
+	d = dst + bytes_per_line;
+	for (i = 0; i < 4; i++, c++)
+		*d++ = CLAMP((*c) >> scalebits);
+
+	d = dst + bytes_per_line*2;
+	for (i = 0; i < 4; i++, c++)
+		*d++ = CLAMP((*c) >> scalebits);
+
+	d = dst + bytes_per_line*3;
+	for (i = 0; i < 4; i++, c++)
+		*d++ = CLAMP((*c) >> scalebits);
+#endif
+}
+
+/*
+ * Copy the 4x4 image block to a CrCb plane buffer
+ *
+ */
+static void copy_image_block_CrCb(const int *src, unsigned char *dst, unsigned int bytes_per_line, unsigned int scalebits)
+{
+#if UNROLL_LOOP_FOR_COPY
+	/* Unroll all loops */
+	const unsigned char *cm = pwc_crop_table+MAX_OUTER_CROP_VALUE;
+	const int *c = src;
+	unsigned char *d = dst;
+
+	*d++ = cm[c[0] >> scalebits];
+	*d++ = cm[c[4] >> scalebits];
+	*d++ = cm[c[1] >> scalebits];
+	*d++ = cm[c[5] >> scalebits];
+	*d++ = cm[c[2] >> scalebits];
+	*d++ = cm[c[6] >> scalebits];
+	*d++ = cm[c[3] >> scalebits];
+	*d++ = cm[c[7] >> scalebits];
+
+	d = dst + bytes_per_line;
+	*d++ = cm[c[12] >> scalebits];
+	*d++ = cm[c[8] >> scalebits];
+	*d++ = cm[c[13] >> scalebits];
+	*d++ = cm[c[9] >> scalebits];
+	*d++ = cm[c[14] >> scalebits];
+	*d++ = cm[c[10] >> scalebits];
+	*d++ = cm[c[15] >> scalebits];
+	*d++ = cm[c[11] >> scalebits];
+#else
+	int i;
+	const int *c1 = src;
+	const int *c2 = src + 4;
+	unsigned char *d = dst;
+
+	for (i = 0; i < 4; i++, c1++, c2++) {
+		*d++ = CLAMP((*c1) >> scalebits);
+		*d++ = CLAMP((*c2) >> scalebits);
+	}
+	c1 = src + 12;
+	d = dst + bytes_per_line;
+	for (i = 0; i < 4; i++, c1++, c2++) {
+		*d++ = CLAMP((*c1) >> scalebits);
+		*d++ = CLAMP((*c2) >> scalebits);
+	}
+#endif
+}
+
+/*
+ * To manage the stream, we keep bits in a 32 bits register.
+ * fill_nbits(n): fill the reservoir with at least n bits
+ * skip_bits(n): discard n bits from the reservoir
+ * get_bits(n): fill the reservoir, returns the first n bits and discard the
+ *              bits from the reservoir.
+ * __get_nbits(n): faster version of get_bits(n), but asumes that the reservoir
+ *                 contains at least n bits. bits returned is discarded.
+ */
+#define fill_nbits(pdec, nbits_wanted) do { \
+   while (pdec->nbits_in_reservoir<(nbits_wanted)) \
+    { \
+      pdec->reservoir |= (*(pdec->stream)++) << (pdec->nbits_in_reservoir); \
+      pdec->nbits_in_reservoir += 8; \
+    } \
+}  while(0);
+
+#define skip_nbits(pdec, nbits_to_skip) do { \
+   pdec->reservoir >>= (nbits_to_skip); \
+   pdec->nbits_in_reservoir -= (nbits_to_skip); \
+}  while(0);
+
+#define get_nbits(pdec, nbits_wanted, result) do { \
+   fill_nbits(pdec, nbits_wanted); \
+   result = (pdec->reservoir) & ((1U<<(nbits_wanted))-1); \
+   skip_nbits(pdec, nbits_wanted); \
+}  while(0);
+
+#define __get_nbits(pdec, nbits_wanted, result) do { \
+   result = (pdec->reservoir) & ((1U<<(nbits_wanted))-1); \
+   skip_nbits(pdec, nbits_wanted); \
+}  while(0);
+
+#define look_nbits(pdec, nbits_wanted) \
+   ((pdec->reservoir) & ((1U<<(nbits_wanted))-1))
+
+/*
+ * Decode a 4x4 pixel block
+ */
+static void decode_block(struct pwc_dec23_private *pdec,
+			 const unsigned char *ptable0004,
+			 const unsigned char *ptable8004)
+{
+	unsigned int primary_color;
+	unsigned int channel_v, offset1, op;
+	int i;
+
+	fill_nbits(pdec, 16);
+	__get_nbits(pdec, pdec->nbits, primary_color);
+
+	if (look_nbits(pdec,2) == 0) {
+		skip_nbits(pdec, 2);
+		/* Very simple, the color is the same for all pixels of the square */
+		for (i = 0; i < 16; i++)
+			pdec->temp_colors[i] = pdec->table_dc00[primary_color];
+
+		return;
+	}
+
+	/* This block is encoded with small pattern */
+	for (i = 0; i < 16; i++)
+		pdec->temp_colors[i] = pdec->table_d800[primary_color];
+
+	__get_nbits(pdec, 3, channel_v);
+	channel_v = ((channel_v & 1) << 2) | (channel_v & 2) | ((channel_v & 4) >> 2);
+
+	ptable0004 += (channel_v * 128);
+	ptable8004 += (channel_v * 32);
+
+	offset1 = 0;
+	do
+	{
+		unsigned int htable_idx, rows = 0;
+		const unsigned int *block;
+
+		/* [  zzzz y x x ]
+		 *     xx == 00 :=> end of the block def, remove the two bits from the stream
+		 *    yxx == 111
+		 *    yxx == any other value
+		 *
+		 */
+		fill_nbits(pdec, 16);
+		htable_idx = look_nbits(pdec, 6);
+		op = hash_table_ops[htable_idx * 4];
+
+		if (op == 2) {
+			skip_nbits(pdec, 2);
+
+		} else if (op == 1) {
+			/* 15bits [ xxxx xxxx yyyy 111 ]
+			 * yyy => offset in the table8004
+			 * xxx => offset in the tabled004 (tree)
+			 */
+			unsigned int mask, shift;
+			unsigned int nbits, col1;
+			unsigned int yyyy;
+
+			skip_nbits(pdec, 3);
+			/* offset1 += yyyy */
+			__get_nbits(pdec, 4, yyyy);
+			offset1 += 1 + yyyy;
+			offset1 &= 0x0F;
+			nbits = ptable8004[offset1 * 2];
+
+			/* col1 = xxxx xxxx */
+			__get_nbits(pdec, nbits+1, col1);
+
+			/* Bit mask table */
+			mask = pdec->table_bitpowermask[nbits][col1];
+			shift = ptable8004[offset1 * 2 + 1];
+			rows = ((mask << shift) + 0x80) & 0xFF;
+
+			block = pdec->table_subblock[rows];
+			for (i = 0; i < 16; i++)
+				pdec->temp_colors[i] += block[MulIdx[offset1][i]];
+
+		} else {
+			/* op == 0
+			 * offset1 is coded on 3 bits
+			 */
+			unsigned int shift;
+
+			offset1 += hash_table_ops [htable_idx * 4 + 2];
+			offset1 &= 0x0F;
+
+			rows = ptable0004[offset1 + hash_table_ops [htable_idx * 4 + 3]];
+			block = pdec->table_subblock[rows];
+			for (i = 0; i < 16; i++)
+				pdec->temp_colors[i] += block[MulIdx[offset1][i]];
+
+			shift = hash_table_ops[htable_idx * 4 + 1];
+			skip_nbits(pdec, shift);
+		}
+
+	} while (op != 2);
+
+}
+
+static void DecompressBand23(struct pwc_dec23_private *pdec,
+			     const unsigned char *rawyuv,
+			     unsigned char *planar_y,
+			     unsigned char *planar_u,
+			     unsigned char *planar_v,
+			     unsigned int   compressed_image_width,
+			     unsigned int   real_image_width)
+{
+	int compression_index, nblocks;
+	const unsigned char *ptable0004;
+	const unsigned char *ptable8004;
+
+	pdec->reservoir = 0;
+	pdec->nbits_in_reservoir = 0;
+	pdec->stream = rawyuv + 1;	/* The first byte of the stream is skipped */
+
+	get_nbits(pdec, 4, compression_index);
+
+	/* pass 1: uncompress Y component */
+	nblocks = compressed_image_width / 4;
+
+	ptable0004 = pdec->table_0004_pass1[compression_index];
+	ptable8004 = pdec->table_8004_pass1[compression_index];
+
+	/* Each block decode a square of 4x4 */
+	while (nblocks) {
+		decode_block(pdec, ptable0004, ptable8004);
+		copy_image_block_Y(pdec->temp_colors, planar_y, real_image_width, pdec->scalebits);
+		planar_y += 4;
+		nblocks--;
+	}
+
+	/* pass 2: uncompress UV component */
+	nblocks = compressed_image_width / 8;
+
+	ptable0004 = pdec->table_0004_pass2[compression_index];
+	ptable8004 = pdec->table_8004_pass2[compression_index];
+
+	/* Each block decode a square of 4x4 */
+	while (nblocks) {
+		decode_block(pdec, ptable0004, ptable8004);
+		copy_image_block_CrCb(pdec->temp_colors, planar_u, real_image_width/2, pdec->scalebits);
+
+		decode_block(pdec, ptable0004, ptable8004);
+		copy_image_block_CrCb(pdec->temp_colors, planar_v, real_image_width/2, pdec->scalebits);
+
+		planar_v += 8;
+		planar_u += 8;
+		nblocks -= 2;
+	}
+
+}
+
+/**
+ * pwc_dec23_decompress - Uncompress a pwc23 buffer.
+ * @pdev: pointer to pwc device's internal struct
+ * @src: raw data
+ * @dst: image output
+ */
+void pwc_dec23_decompress(struct pwc_device *pdev,
+			  const void *src,
+			  void *dst)
+{
+	int bandlines_left, bytes_per_block;
+	struct pwc_dec23_private *pdec = &pdev->dec23;
+
+	/* YUV420P image format */
+	unsigned char *pout_planar_y;
+	unsigned char *pout_planar_u;
+	unsigned char *pout_planar_v;
+	unsigned int   plane_size;
+
+	mutex_lock(&pdec->lock);
+
+	bandlines_left = pdev->height / 4;
+	bytes_per_block = pdev->width * 4;
+	plane_size = pdev->height * pdev->width;
+
+	pout_planar_y = dst;
+	pout_planar_u = dst + plane_size;
+	pout_planar_v = dst + plane_size + plane_size / 4;
+
+	while (bandlines_left--) {
+		DecompressBand23(pdec, src,
+				 pout_planar_y, pout_planar_u, pout_planar_v,
+				 pdev->width, pdev->width);
+		src += pdev->vbandlength;
+		pout_planar_y += bytes_per_block;
+		pout_planar_u += pdev->width;
+		pout_planar_v += pdev->width;
+	}
+	mutex_unlock(&pdec->lock);
+}